jshetaye's profile picture. CS BSc & MSc @ Stanford, systems sw

Joseph Shetaye

@jshetaye

CS BSc & MSc @ Stanford, systems sw

Joseph Shetaye đã đăng lại

Introducing 𝘁𝗵𝗼𝘂𝗴𝗵𝘁𝗯𝘂𝗯𝗯𝗹𝗲𝘀: a *fully unsupervised* LM for input-adaptive parallel latent reasoning ✅ Learn yourself a reasoning model with normal pretraining ✅ Better perplexity compared to fixed thinking tokens No fancy loss, no chain of thought labels 🚀

houjun_liu's tweet image. Introducing 𝘁𝗵𝗼𝘂𝗴𝗵𝘁𝗯𝘂𝗯𝗯𝗹𝗲𝘀: a *fully unsupervised* LM for input-adaptive parallel latent reasoning

✅ Learn yourself a reasoning model with normal pretraining
✅ Better perplexity compared to fixed thinking tokens

No fancy loss, no chain of thought labels 🚀

Joseph Shetaye đã đăng lại

Happy Throughput Thursday! We’re excited to release Tokasaurus: an LLM inference engine designed from the ground up for high-throughput workloads with large and small models. (Joint work with @achakravarthy01, @ryansehrlich, @EyubogluSabri, @brad19brown, @jshetaye,…

jordanjuravsky's tweet image. Happy Throughput Thursday! We’re excited to release Tokasaurus: an LLM inference engine designed from the ground up for high-throughput workloads with large and small models.

(Joint work with @achakravarthy01, @ryansehrlich, @EyubogluSabri, @brad19brown, @jshetaye,…

United States Xu hướng

Loading...

Something went wrong.


Something went wrong.